Dexin Peng, Xiaoyu Wang · 2026 · SSRN Electronic Journal
DOI: 10.2139/ssrn.7528558 · cited by 0 works (OpenAlex) · open-access PDF
Shallow-Modelle sind spezielle Fälle von tiefen Modellen, und tiefe Modelle haben theoretisch das Potenzial, die flachen Modelle zu übertreffen. Allerdings bietet die bestehende empirische Asset-Preisierungsliteratur starke Benchmarks für flache Modelle. Residual Learning ermöglicht es neuronalen Netzwerkmodellen in der Asset-Preisierung, tiefer zu gehen, indem sie ihre flachen Gegenstände bewahren und verfeinern. Das Sharpe-Verhältnis für wertgewogene langfristige Portfolios von tiefen Restmodellen (2.07) ist höher als das für die entsprechenden flachen Modelle (1.92) und mehr als doppelt so hoch wie bei den tiefen Feedforward-Modellen (0.89).
Machine translation (Meta M2M100); the English original follows.
Shallow models are special cases of deep models, and deep models theoretically have the potential to outperform the shallow ones. However, the existing empirical asset pricing literature provides strong benchmarks for shallow models. Residual learning allows neural network models in asset pricing to go deeper by preserving and refining their shallow counterparts. The out-of-sample Sharpe ratio for value-weighted long-short portfolios of deep residual models (2.07) is higher than that for the corresponding shallow ones (1.92) and more than twice that of the deep feedforward models (0.89). We sh
Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese
Topics: Capital asset pricing model, Residual, Consumption-based capital asset pricing model, Asset (computer security), Arbitrage pricing theory, Econometrics
GET https://store.agentexchange.work/gw/papers/verify?title=...&year=... (0.003 USD), fetch this record as JSON with /gw/papers/paper?id=2610.09613, or list what it cites with /gw/papers/references?id=.... Pay per call in USDC (x402) or with a 19 USD card key for 1,000 calls. Catalogue · llms.txtSources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange